The Divinity Developer Details Its Implementation of Generative AI for New Project

The developer behind acclaimed role-playing games like Baldur's Gate 3 and Divinity: Original Sin has recently teased its next major project, creating immense hype within the gaming community. However, subsequent statements from the company's lead designer have added nuance to the conversation, touching on the studio's approach toward machine learning.

A Tool for Ideation, Not Replacement

In a recent statement, Larian's director detailed that the developer is using machine learning for particular preliminary functions. These involve enhancing pitch decks, generating rough artistic references, and creating temporary copy.

Importantly, Vincke made clear that the final assets in the game will be crafted exclusively by human writers. "Larian is developing every line in-house," he affirmed.

We are actively expanding our team of storytellers and are currently assembling writing teams.

As this area is being specifically called out — we presently have over twenty artistic staff and have job openings for further talent.

All our efforts we do is supplementary and focused on having people spend more time on making content.

Every ML tool used well is additive to a artist's routine, never a stand-in for their talent.

Responding to Feedback and Defining the Path

The admission of employing this technology initially sparked backlash among a segment of the fanbase. In response, Vincke provided additional detail on social media.

"We use machine learning to explore references, in the same way we use the internet and physical media," he wrote. "During the initial ideation stages we use it as a rough outline for composition which we then swap out with hand-crafted illustrations."

He added, "Our studio recruits creatives for their unique talent, not for their willingness to follow what a algorithm proposes."

Focused Uses for Machine Learning

Vincke had previously detailed the team's practical method to AI and ML, grouping its use into primary functions:

• Automation of Tedious Tasks: Areas like motion capture cleaning, dialogue cleanup, and pipeline-specific tasks like adjusting assets for various species.
• Rapid Prototyping ('White Boxing'): Using systems to rapidly prototype simple mock-ups of mechanics to test concepts before full implementation.
• Future Potential for Gameplay: Exploring how AI could in the future enhance emergent player agency, especially in simulating player-driven narratives in a vast role-playing world.

He clearly noted that central narrative disciplines — including music composition — are are absolutely not departments where the team is reducing artistic input. In fact, Larian is actively hiring in these exact positions.

"Our studio is neither shipping a game with machine-made assets, and we are certainly not considering cutting staff to replace them with AI," Vincke summarized.